Hevy MCP

Overview

Hevy MCP is a lightweight, TypeScript‑based Model Context Protocol server that bridges the gap between AI assistants and the Hevy workout tracking platform. By exposing a single, well‑defined tool——the server allows LLMs such as Claude to pull a user’s exercise history directly from Hevy, enabling data‑driven fitness coaching and analysis without manual export or API integration. This solves the common pain point of having to manually transfer workout logs into an AI‑powered workflow, streamlining the process for developers and fitness enthusiasts alike.

The server implements the MCP specification using the official SDK, ensuring that the tool signatures and response schemas are fully typed and validated with Zod. Developers can configure the server via a simple environment variable () and launch it with any Node.js runtime. Once registered in an LLM’s MCP configuration, the assistant can issue natural‑language requests such as “Summarize my last five workouts” or “Recommend a training plan based on my recent lifts.” The assistant then calls , receives structured JSON data, and can perform further reasoning or generate tailored recommendations.

Key capabilities include:

• Secure data access: The server authenticates against Hevy using a personal API key, keeping credentials isolated from the LLM.
• Pagination support: accepts page and limit parameters, allowing assistants to retrieve large histories incrementally.
• Schema‑driven validation: Zod ensures that every response adheres to the expected shape, preventing runtime errors in downstream logic.
• Minimal overhead: The implementation is intentionally small—just one tool and a few configuration lines—making it easy to drop into existing MCP setups.

Real‑world use cases span personal coaching apps, automated progress reports, and hybrid training programs where an AI assistant can synthesize past performance to suggest next‑step workouts. For developers building fitness platforms, Hevy MCP provides a plug‑and‑play bridge that eliminates the need for custom API wrappers or manual data pipelines. Its straightforward integration with any MCP‑compliant LLM means that teams can focus on higher‑level logic and user experience, while the server handles secure, reliable data retrieval from Hevy.